Skills/PyPI/prime-intellect-mcp

prime-intellect-mcp@0.1.0

CAUTION· static only

Publisher claims: "MCP server that lets Claude Code (and any MCP client) rent, drive, and terminate Prime Intellect GPU pods autonomously, with built-in spend caps." Observed in sandbox: static analysis only — behavior not yet observed.

Registry PyPI (MCP server)Publisher kvrancic · publishing for 194 daysInstalls 48Last detonated 3 h ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Before you give it your token

It will ask for
PRIME_API_KEYConfiguration, not credentials: PRIME_INTELLECT_MCP_STATE_DIR, PRIME_MAX_HOURLY_USD, PRIME_MAX_TOTAL_USD
Where it talks to
primeintellect.ai (its own)
What the honeypot saw
nothing has run yet
What we could not test
everything: the server has not run yet

Run it before you trust it. Nothing has run yet: the code was read, the server was not. `vet-skills try` runs this exact version in the honeypot in about a minute.

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-15 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions; Access to sensitive file paths; Collapsed <details> block carrying instructions. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Python subprocess execution detectedtests/test_smoke_live.py:116 · Python subprocess execution detectedproc = subprocess.run(args, capture_output=True, text=True, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:191 · Collapsed <details> block carrying instructions<summary><b><code>ssh: Permission denied (publickey)</code></b></summary> You haven't told Prime Intellect about your public key (or the pod was provisioned befFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathssrc/prime_intellect_mcp/server.py:454 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"Ensure you've run `prime config set-ssh-key-path ~/.ssh/id_ed25519` "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:161 · Collapsed <details> block carrying instructions<summary><b><code>PRIME_API_KEY is not set</code></b></summary> Either your Claude Code config didn't pick up the `env` block, or you typed `PRIME_API_KEY` as aFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:179 · Collapsed <details> block carrying instructions<summary><b><code>Quote token expired</code></b></summary> Quotes live 60 seconds; the agent waited too long between `pod_quote` and `pod_create`. Just call `poFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
References a credential file in the home directorysrc/prime_intellect_mcp/server.py:454 · References a credential file in the home directory"Ensure you've run `prime config set-ssh-key-path ~/.ssh/id_ed25519` "Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03

Cost to the agent

Instructions loaded
≈76 tok
1 file · 27 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for prime-intellect-mcp@0.1.0 as of 2 h ago. This is the package itself, not its dependencies.

What would make this Verified

25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim kvrancic: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim kvrancicPropose a patch to the maintainer